Please use this identifier to cite or link to this item:
|Title:||Toward Global Automatic Built-Up Area Recognition Using Optical VHR Imagery|
|Authors:||PESARESI Martino; EHRLICH Daniele; CARAVAGGI Ivano; KAUFFMANN MAYEUL; LOUVRIER Christophe|
|Citation:||IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING vol. 4 no. 4 p. 923-934|
|Publisher:||IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC|
|Type:||Articles in Journals|
|Abstract:||The work presented here tests an automatic procedure able to recognize the presence of built-up areas in the satellite images with the output nominal scale of 1:50.000. The input data is a set of 54 Ikonos and Quick Bird scenes considered as representative of the variety of human settlement patterns in large cities at global level. The methodology for automatic image information extraction is based on calculation of anisotropic rotation-invariant textural grey-level co-occurrence measures, also called PANTEX methodology. The total area analyzed covers 35000 km2. The data under test shows high variety in latitude, season, sun elevation and sun azimuth at the time of image data collection. The output of the automatic image information retrieval is evaluated by comparison with a collection of reference information visually interpreted from the same satellite data input. Two complementary evaluation strategies are presented here: i) interactive selection of one threshold level in the textural measurement and then unsupervised application of the same threshold level to all the datasets under test, and ii) per-scene optimization of the threshold based on the available reference samples. This work briefly summarizes the nature of the errors and implications for global settlement classification.|
|JRC Institute:||Institute for the Protection and Security of the Citizen|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.